preview_transaction

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It explicitly states it is read-only, never signs or broadcasts, and describes what it checks (dangerous patterns) and returns (verdict + human-readable list). It also mentions live on-chain context reading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single coherent paragraph that starts with main purpose, then details checks, and ends with usage guidance. It is informative but slightly long; however, every sentence adds value and is well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so description must explain return values. It does so by stating it returns a SAFE/REVIEW/DANGER verdict with a plain-English list. It covers all necessary aspects for an agent to decide when to call this tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. The description adds meaning beyond schema: lists supported chains for the chain parameter, explains to as contract/recipient, data as calldata (optional for pure transfer), and value in wei. This enhances understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool decodes and explains an EVM transaction before signing, returning a verdict with plain-English list. It specifies inputs (chain, to, data, value) and distinguishes from sibling decode_calldata by focusing on pre-signing safety analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use this whenever an agent is about to sign or relay a transaction it didn't fully construct.' This provides clear when-to-use guidance, though it does not explicitly state when not to use or compare with siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.